ReTraCk
Reported on 10 benchmarks across 1 task
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Natural Language Processing10 results
- 71best: 83.5 (ChatKBQA)
- Hits@171.6best: 86.4 (ChatKBQA)
- Compositional EM61.5
- Compositional F170.9
- I.I.D. EM84.4
- I.I.D. F187.5
- Overall EM58.1
- Overall F165.3
- Zero-shot EM44.6
- Zero-shot F152.5